A Note on the Scale Efficiency Test of Simar and Wilson
|
|
- Estella Brooks
- 5 years ago
- Views:
Transcription
1 International Journal of Business Social Science Vol. No. 4 [Special Issue December 0] Abstract A Note on the Scale Efficiency Test of Simar Wilson Hédi Essid Institut Supérieur de Gestion Université de Tunis 4, Rue de la Liberté, Cité Bouchoucha Le Bardo-Tunis, Tunisie Pierre Ouellette Department of Economics Université du Québec à Montréal PO Box 8888, Station Centre-Ville Montréal, Québec Canada H3C 3P8 Stéphane Vigeant IESEG School of management EQUIPPE (Universités de Lille) Université des Sciences et Technologies de Lille Villeneuve d Ascq Cédex France Simar Wilson (00) procedure to test for returns to scale has a drawbac as it may generates inconsistent values. We use a counter example to show that their returns to scale test procedure generates non admissible pseudo-values. Consequently, the test results are not consistent cannot be used to test for returns to scale. We propose a remedy that consists in a correction of the simulation algorithm to ensure the consistency of the estimated test statistic. Keywords: Returns to scale, Data envelopment analysis, Bootstrap, Test of hypothesis. JEL Classifications: C3; C4; D0. Introduction Simar Wilson (00) bootstrap method offers a hypothesis testing procedure for returns to scale that is interesting seems very satisfactory as it does not suffer from the convergence problem of the others. The procedure is based on the efficiency scale ratio developed by Färe Grossopf (985) this opens the door to some a potential problem that we address here. Färe Grossopf scale efficiency measure is defined as the ratio of two efficiency scores, those being measured under two different assumptions on the return to scale. By construction, these measures are always bounded by one. This must hold because the data are generated under only one Data Generating Process (the true one) that belongs to either one or the other assumption. In the bootstrap simulations proposed by Simar Wilson the efficiency scores are generated from two different Data Generating Processes (DGP). This is not consistent with the theory might ultimately lead to values of the score that are not admissible: in a simple example we show that the scale efficiency pseudo-scores may easily end up taing values above one this is clearly not allowed, by definition. The problem is traced bac to the construction of the DGP for the simulations. To correct this problem, we develop a smooth bootstrap method that guaranties that the pseudo-scores of the efficiency scale have all admissible values. This feature allows us to anchor the test procedure to a consistent DGP of the scale efficiencies. Recently, Kneip et al. (008, 009) developed a consistent bootstrap method for inference about the efficiency of a single, fixed point. However, this method requires complicated coding is not appropriate for approximating the sampling distribution of a test statistic (Simar Wilson, 0). 3
2 The Special Issue on Business, Humanities Social Science Centre for Promoting Ideas, USA. Production technology returns to scale Consider a production activity that uses the sets of inputs, i,,, y y,,, r r s. The production possibility set of this activity is defined as:, ms, is feasible x x i m to produce the output vector, x y x y. () The returns to scale of the firms are characterized by the way one can either exp the scale in the production set or shrin it or both. That is, the technology exhibits non increasing (nirs), non decreasing (ndrs) or constant () returns to scale depending on the value assumed by the positive scalar α in the following set: x, y x, y for all, for =nirs, ndrs () nirs ndrs where [0,), [, ) [0, ). A technology that exhibits ndrs, nirs or in different regions of the production frontier is said to be characterized by variable returns to scale (). This production possibility set is denoted. It is possible to define an input oriented technical efficiency measure in the sense of Farrell (957) with respect to the various assumptions concerning the returns to scale. That is: x, y min x, y, where = nirs, ndrs, (3) From Färe Grossopf (985), the (technical) efficiency measures defined in (3) can be used to construct scale efficiency measures for each organization. A scale efficiency measure is the ratio of the efficiency measure under technology a type technology. That is: S x, y x, y/ x, y. (4) We say that the production technology is of the type if technology when, nirs,, /, When, one, i.e. S x y, it is said to exhibit increasing returns to scale. S x, y. To determine the returns to scale of the S x y we compute a second ratio that is less restrictive than the initial ratio. That is: S x y x y x y. (5) S x y the technology is said to exhibit decreasing returns to scale for values strictly less than, 3. Efficiency estimation statistical model Because they are unnown, the efficiency measures must be estimated. Given a sample of n observations, 0 n x, y, a stard Data Envelopment Analysis (DEA) estimator is constructed to assess the Decision Maing Units (DMU) efficiency. The smallest convex envelop of the sample gives the DEA estimator of in the case. That is: ˆ ms n n n x, y x x, y y,,, n (6) To obtain the estimators for the other types of returns to scale, ˆnirs constraint on the sum of the. That is, in the nirs case we have n ˆ it is sufficient to slightly alter the to obtain a envelop, one simply removes the summation constraints on the, but obviously eeps the non negativity of the λs. Farrell s efficiency measures are obtained by substituting ˆ for in equations (3). This gives: ˆ, min, ˆ x y x y =, nirs. (7) We suppose that the production set is closed, satisfies free disposal of inputs, is bounded for finite inputs positive outputs require positive inputs. These are stard assumptions on the technology are discussed in Färe (988), among others. 33
3 International Journal of Business Social Science Vol. No. 4 [Special Issue December 0] The resulting scale ratio estimators are S ˆ ˆ x, y/ ˆ x, y ˆ ˆ nirs, / ˆ, S x y x y. To ensure the consistency of the estimator, it is necessary to specify a statistical model that allows us to fully characterize the DGP. This is the content of the following assumptions. n Assumption A: The set of observations, x y are identically independently distributed (i.i.d.) rom variables with probability density function f x, y defined on. Assumption A: The probability density function f x, y is continuous on the interior of, f x y, y 0 where x y x, yx is any point on the frontier of. Assumption A3: The efficiency measure xy, is differentiable in x y. Assumption A, A A3 together define the statistical model that allows us to characterize the DGP, denoted. In fact, the DGP is entirely characterized by the production possibility set the density f. That is,, f. 4. Bootstrapping Test Statistics for Returns to Scale The test procedure is in two steps. The first step consists in testing the null that a given combinations xy, is scale efficient, i.e. its technology is of the type. The alternative hypothesis has to be less restrictive. One natural hypothesis is that the combination xy, is characterized by a -technology. Then we have: 0 Test #: H : S x, y H : S x, y A If the hypothesis H 0 is reected, we still have to identify whether the returns to scale are increasing or decreasing. This will wor if we can find a new null hypothesis that is less restrictive than the one in the first test. One way of doing this is to suppose that under the null hypothesis the combination xy, is subect to decreasing returns to scale (drs). Then, the alternative hypothesis would be that the combination xy, is subect to an increasing return to scale (irs) technology, since constant returns to scale have already been reected in the first test. Thus, the second test is: ' Test # : H : S x, y 0 ' H A : S x, y The test statistics for the first second test are S ˆ ˆ x, y/ ˆ x, y ˆ, /, S x y x y, respectively. To apply these tests we need to find an approximation of the sampling distribution of the estimators of both scale efficiency ratios,. This approximation rests on the bootstrap method that consists in identically replicating the empirical DGP many times study the behavior this set of bootstrapped estimates. To implement the procedure, we first generate, from the original sample 0, B pseudo-samples: b, b,, B. Then, the original estimation method (DEA in our case) is applied to each pseudo-samples to obtain the bootstrap estimator of the test statistic for ( for ) which are functions of, ˆ nirs. To generate the pseudo-efficiencies ˆ,,, nirs, we use a homogenous bootstrap methodology developed by Simar Wilson (998). This procedure rests on the assumption that the efficiency structure is, f, y f. homogenous. 3 That is, the efficiency score is independent of y : ˆ ˆ 3 Because Farrell s measure is radial, we are allowed to write the input vector x in polar coordinates. That is, the modulus of T m x x x x the angle is x 0, /. This allows us to write the density as (, ),, x is 34 f x y f y.
4 The Special Issue on Business, Humanities Social Science Centre for Promoting Ideas, USA A consistent estimator of f, obtained using a ernel estimator corrected by Schuster s (985) Silverman (985) is defined as follows: ˆ g ˆ( t ) if t ˆ ˆ f c () n t t t 0 otherwise, where gˆ t. (8) nh h h We use a normal Gaussian ernel, denoted, the bwidth, h, is set following the normal reference rule (Silverman (986)). In the procedure proposed by Simar et Wilson (00), the pseudo-scores ˆ,,, nirs are generated from f ˆ c, independently from the null hypothesis. The five step procedure to recover the simulated efficiencies is: Step : Given, compute ˆ ˆ,,, x y n using equation (7). Step : Generate smoothed resampled pseudo-efficiencies as follows. First generate,,, n by resampling with replacement a sample of size n, from the empirical distribution ˆ,,, n. Then generate the sequence,,, n as follows: h if h h otherwise, where N 0, Then, generate the pseudo-efficiencies Step 3: Compute the pseudo variable inputs,. using / / ˆ ˆ (/ ) ˆ x x. h where (/ n). Step 4: Compute the bootstrapped efficiency measures ˆ using the pseudo variable inputs based on the following program: ˆ n n n x, y min x x, y y,, 0 if =. When = nirs or =, it is sufficient to slightly alter the constraint on the sum of the. That is, in the nirs case we have n, to obtain a envelop, no constraints on the are necessary, other than the non negativity ones. Step 5: Repeat steps -5 B times to obtain B efficiency measures ˆ,,,,,, b n b B. This algorithm is repeated for each type of returns to scale, =, nirs, the simulation results are used to compute the pseudo-scores ˆ ˆ ˆ S / ˆ ˆ nirs ˆ S /. These simulated values are used to estimate the empirical distribution of ˆ ˆ S S ( of course S ˆ S ˆ ), the one used to approximate the unnown distribution of the statistic S ˆ S. Simar de Wilson (00) procedure does not tae internalize the null hypothesis however when generating the pseudo-scores ˆ,,,,,,,,, b n b B nirs. This is a problem because this procedure may well returns non admissible values of the scale efficiency estimates. That is, as we show in our example below, it may well be possible to obtain test statistic above one, ˆ S or S ˆ. To solve this problem, we propose to tae into account the null hypothesis in the pseudo-scores generation procedure. The algorithm of Simar Wilson (00) is adusted in this case as follows: ˆ ˆ x, y,, n using equation (7). Step : Compute Steps 3: As above. n 35
5 International Journal of Business Social Science Vol. No. 4 [Special Issue December 0] Step 4: Compute the bootstrapped efficiency measures ˆ using the pseudo variable inputs based on the following program: ˆ x, y min x n x, y n y, 0 ; ˆ n n n x, y min x,,, 0 x y y. Step 5: Repeat steps -5 B times to obtain B efficiency measures ˆ,,,,,,,, b n b B. If the test concludes that we reect the null hypothesis, then one conduct the second test. To generate the data in this second case, we use the following: ˆ nirs ˆ nirs x, y,, n using equation (7). Step : Compute Steps 3: As above. Step 4: Compute the bootstrapped efficiency measures ˆ nirs ˆ using the pseudo variable inputs based on the following program: ˆ nirs n n n x, y min x x, y y,, 0 ; ˆ n n n x, y min x,,, 0 x y y. Step 5: Repeat steps -5 B times to obtain B efficiency measures ˆ,,,,,,,, b n b B nirs. The correction we have made to the algorithm of Simar et Wilson (00) ensures that the values assumed by ˆ ˆ ˆ S / ˆ ˆ nirs / ˆ S are all admissible. That is, ˆ S S ˆ. 5. An Example To illustrate the difference between the two procedures, we use a simple example based on six DMU producing one output with two inputs. Table : The Data DMU Output Input Input A B C D E 7 F 4 The tables below present the results for ten bootstrap simulations, B=0. (We have decided to eep the size of the problem manageable not complicate it through unnecessary computations.) The first two tables presents the results using the approach proposed by Simar Wilson (00) then the next two tables present the results with our proposed method. These simulations are conducted using a SAS program developed by the authors. Tables 3 presents the simulation results for based on Simar Wilson (00). In both tables, the first column gives the initial value of the score, that is either or. The rest of the tables consist of the pseudo-values. In the Table, there are seven pseudo values that are larger than one, that is >. These pseudo scale efficiency measures are deemed not admissible. Table contains one pseudo-value that exceeds one,. > 36
6 The Special Issue on Business, Humanities Social Science Centre for Promoting Ideas, USA Table : Pseudo-scores for (Simar et Wilson approach) Initial value COL COL COL3 COL4 COL5 COL6 COL7 COL8 COL9 COL0 0,9693 0,9594 0, , , ,9503 0,8794 0,6693 0,84968,06939,03 0,97476, , ,7834,0004,0373 0, ,875658, , ,7873 0, , , ,99553, ,9447 0, ,9360 0,7959 0, , , , ,996 0, , , ,7845 0, , ,8894 0,87906 Table 3: Pseudo-scores for (Simar et Wilson approach) Initial value COL COL COL3 COL4 COL5 COL6 COL7 COL8 COL9 COL0 0, , , ,998 0, , ,9978 0,999 0, ,9965 0, , ,9984 0, ,93768,0005 0, , , ,7879 0, , ,88873 Table 4 5 present the simulation results after we corrected Simar Wilson s algorithm. These results present no anomalies, all pseudo values are less than or equal to one, as expected. Table 4: Corrected pseudo-scores for Initial value COL COL COL3 COL4 COL5 COL6 COL7 COL8 COL9 COL0 0,9693 0,9594 0, , , ,9503 0,8794 0,6693 0, , , , , , , , , , , , , , , , ,9898 0, ,983 0, ,7959 0, , , , ,996 0, , , ,7845 0, , ,8894 0,87906 Table 5: Corrected pseudo-scores for Initial value COL COL COL3 COL4 COL5 COL6 COL7 COL8 COL9 COL0 0, , , ,983 0,7959 0, , , ,996 0, , , ,7845 0, , ,8894 0, Conclusion In this note we have developed a procedure to test non parametric statistical hypothesis concerning the scale efficiency of organization. Because there is no asymptotic distribution for the test statistic under the null hypothesis, we used a smooth bootstrap methodology to approximate it. This approach allows us to estimate the p-values of the test to determine a decision rule to accept or reect the null hypothesis. The main characteristic of our test is its consistency under the null hypothesis. In the procedure developed by Simar Wilson (00), the data generating process to generate the test statistic may return values that are above one, which is not possible theoretically. Our procedure corrects this flaw allows us to test the returns to scale with a consistent test. 37
7 International Journal of Business Social Science Vol. No. 4 [Special Issue December 0] References Farrell, M. J. (957). The Measurement of Productive Efficiency. Journal of the Royal Statistical Society, Series A, 0 (3), Färe, R. (988). Fundamentals of Production Theory. Lecture Notes in Economics Mathematical Systems, 3, Springer-Verlag, Berlin Heidelberg. Färe, R., & Grossopf, S. (985). A Nonparametric Cost Approach to Scale Efficiency. Scinavian Journal of Economics, 87, Kneip, A., Simar, L., & Wilson, P. W. (009). A Computationally efficient, consistent bootstrap for inference with non-parametric DEA estimators. Discussion Paper No. 0903, Institut de Statistique, Université Catholique de Louvain, Louvain-la-Neuve, Belgium. Kneip, A., Simar, L., & Wilson, P. W. (008). Asymptotics consistent bootstraps for DEA estimators in nonparametric frontier models. Econometric Theory, 4, Schuster, E. F., (985). Incorporating Support Constraints into Nonparametric Estimators of Densities. Communications in Statistics-Theory Method, 4, Silverman, B. W. (986). Density Estimation for Statistics Data Analysis. New Yor: Chapman Hall. Simar, L., & Wilson, P. W. (0). Inference by the m out of n bootstrap in nonparametric frontier models. Journal of Productivity Analysis, 36, Simar, L., & Wilson, P. W. (00). Non-parametric tests of returns to scale. European Journal of Operational Research, 39, 5-3. Simar, L., & Wilson, P. W. (998). Sensitivity Analysis of Efficiency Scores: How to Bootstrap in Nonparametric Frontier Models. Management Science, 44,
I N S T I T U T D E S T A T I S T I Q U E B I O S T A T I S T I Q U E E T S C I E N C E S A C T U A R I E L L E S (I S B A)
I N S T I T U T D E S T A T I S T I Q U E B I O S T A T I S T I Q U E E T S C I E N C E S A C T U A R I E L L E S (I S B A) UNIVERSITÉ CATHOLIQUE DE LOUVAIN D I S C U S S I O N P A P E R 2011/35 STATISTICAL
More informationSensitivity Analysis of Efficiency Scores: How to Bootstrap in Nonparametric Frontier Models. April Abstract
Sensitivity Analysis of Efficiency Scores: How to Bootstrap in Nonparametric Frontier Models by Léopold Simar and Paul W. Wilson April 1995 Abstract Efficiency scores of production units are generally
More informationSlack and Net Technical Efficiency Measurement: A Bootstrap Approach
Slack and Net Technical Efficiency Measurement: A Bootstrap Approach J. Richmond Department of Economics University of Essex Colchester CO4 3SQ U. K. Version 1.0: September 2001 JEL Classification Code:
More informationA better way to bootstrap pairs
A better way to bootstrap pairs Emmanuel Flachaire GREQAM - Université de la Méditerranée CORE - Université Catholique de Louvain April 999 Abstract In this paper we are interested in heteroskedastic regression
More informationSubhash C Ray Department of Economics University of Connecticut Storrs CT
CATEGORICAL AND AMBIGUOUS CHARACTERIZATION OF RETUNS TO SCALE PROPERTIES OF OBSERVED INPUT-OUTPUT BUNDLES IN DATA ENVELOPMENT ANALYSIS Subhash C Ray Department of Economics University of Connecticut Storrs
More informationBootstrap for model selection: linear approximation of the optimism
Bootstrap for model selection: linear approximation of the optimism G. Simon 1, A. Lendasse 2, M. Verleysen 1, Université catholique de Louvain 1 DICE - Place du Levant 3, B-1348 Louvain-la-Neuve, Belgium,
More informationI N S T I T U T D E S T A T I S T I Q U E B I O S T A T I S T I Q U E E T S C I E N C E S A C T U A R I E L L E S (I S B A)
I N S T I T U T D E S T A T I S T I Q U E B I O S T A T I S T I Q U E E T S C I E N C E S A C T U A R I E L L E S (I S B A) UNIVERSITÉ CATHOLIQUE DE LOUVAIN D I S C U S S I O N P A P E R /33 EXPLAINING
More informationData Envelopment Analysis within Evaluation of the Efficiency of Firm Productivity
Data Envelopment Analysis within Evaluation of the Efficiency of Firm Productivity Michal Houda Department of Applied Mathematics and Informatics Faculty of Economics, University of South Bohemia in Česé
More informationA Test of Cointegration Rank Based Title Component Analysis.
A Test of Cointegration Rank Based Title Component Analysis Author(s) Chigira, Hiroaki Citation Issue 2006-01 Date Type Technical Report Text Version publisher URL http://hdl.handle.net/10086/13683 Right
More informationStochastic Nonparametric Envelopment of Data (StoNED) in the Case of Panel Data: Timo Kuosmanen
Stochastic Nonparametric Envelopment of Data (StoNED) in the Case of Panel Data: Timo Kuosmanen NAPW 008 June 5-7, New York City NYU Stern School of Business Motivation The field of productive efficiency
More informationRegression and Inference Under Smoothness Restrictions
Regression and Inference Under Smoothness Restrictions Christopher F. Parmeter 1 Kai Sun 2 Daniel J. Henderson 3 Subal C. Kumbhakar 4 1 Department of Agricultural and Applied Economics Virginia Tech 2,3,4
More informationFast Bootstrap for Least-square Support Vector Machines
ESA'2004 proceedings - European Symposium on Artificial eural etworks Bruges (Belgium), 28-30 April 2004, d-side publi., ISB 2-930307-04-8, pp. 525-530 Fast Bootstrap for Least-square Support Vector Machines
More informationResearch Article A Data Envelopment Analysis Approach to Supply Chain Efficiency
Advances in Decision Sciences Volume 2011, Article ID 608324, 8 pages doi:10.1155/2011/608324 Research Article A Data Envelopment Analysis Approach to Supply Chain Efficiency Alireza Amirteimoori and Leila
More informationData envelopment analysis
15 Data envelopment analysis The purpose of data envelopment analysis (DEA) is to compare the operating performance of a set of units such as companies, university departments, hospitals, bank branch offices,
More informationD I S C U S S I O N P A P E R
I N S T I T U T D E S T A T I S T I Q U E B I O S T A T I S T I Q U E E T S C I E N C E S A C T U A R I E L L E S ( I S B A ) UNIVERSITÉ CATHOLIQUE DE LOUVAIN D I S C U S S I O N P A P E R 213/54 Unobserved
More informationA new approach to stochastic frontier estimation: DEA+
A new approach to stochastic frontier estimation: DEA+ Dieter Gstach 1 Working Paper No. 39 Vienna University of Economics August 1996 1 University of Economics, VWL 6, Augasse 2-6, 1090 VIENNA, Austria.
More informationHypothesis Testing with the Bootstrap. Noa Haas Statistics M.Sc. Seminar, Spring 2017 Bootstrap and Resampling Methods
Hypothesis Testing with the Bootstrap Noa Haas Statistics M.Sc. Seminar, Spring 2017 Bootstrap and Resampling Methods Bootstrap Hypothesis Testing A bootstrap hypothesis test starts with a test statistic
More informationT E C H N I C A L R E P O R T A FULLY NON PARAMETRIC STOHASTIC FRONTIER MODEL FOR PANEL DATA. ANDERSON D.J., and L. SIMAR
T E C H N I C A L R E P O R T 0542 A FULLY NON PARAMETRIC STOHASTIC FRONTIER MODEL FOR PANEL DATA ANDERSON D.J., and L. SIMAR * I A P S T A T I S T I C S N E T W O R K INTERUNIVERSITY ATTRACTION POLE http://www.stat.ucl.ac.be/iap
More informationDouble Bootstrap Confidence Intervals in the Two Stage DEA approach. Essex Business School University of Essex
Double Bootstrap Confidence Intervals in the Two Stage DEA approach D.K. Chronopoulos, C. Girardone and J.C. Nankervis Essex Business School University of Essex 1 Determinants of efficiency DEA can be
More informationHeteroskedasticity-Robust Inference in Finite Samples
Heteroskedasticity-Robust Inference in Finite Samples Jerry Hausman and Christopher Palmer Massachusetts Institute of Technology December 011 Abstract Since the advent of heteroskedasticity-robust standard
More informationDerivative Properties of Directional Technology Distance Functions
Derivative Properties of Directional Technology Distance Functions Lane Blume Hudgins 1 and Daniel Primont 2 1 Department of Economics Southern Illinois University Carbondale Carbondale, Illinois 62901,
More informationProduct-limit estimators of the survival function with left or right censored data
Product-limit estimators of the survival function with left or right censored data 1 CREST-ENSAI Campus de Ker-Lann Rue Blaise Pascal - BP 37203 35172 Bruz cedex, France (e-mail: patilea@ensai.fr) 2 Institut
More informationA Goodness-of-fit Test for Copulas
A Goodness-of-fit Test for Copulas Artem Prokhorov August 2008 Abstract A new goodness-of-fit test for copulas is proposed. It is based on restrictions on certain elements of the information matrix and
More informationA measure of radial asymmetry for bivariate copulas based on Sobolev norm
A measure of radial asymmetry for bivariate copulas based on Sobolev norm Ahmad Alikhani-Vafa Ali Dolati Abstract The modified Sobolev norm is used to construct an index for measuring the degree of radial
More informationNEGATIVE DATA IN DEA: A SIMPLE PROPORTIONAL DISTANCE FUNCTION APPROACH. Kristiaan Kerstens*, Ignace Van de Woestyne**
Document de travail du LEM 2009-06 NEGATIVE DATA IN DEA: A SIMPLE PROPORTIONAL DISTANCE FUNCTION APPROACH Kristiaan Kerstens*, Ignace Van de Woestyne** *IÉSEG School of Management, CNRS-LEM (UMR 8179)
More informationTesting over-representation of observations in subsets of a DEA technology
Testing over-representation of observations in subsets of a DEA technology by Mette Asmild, Jens Leth Hougaard and Ole B. Olesen Discussion Papers on Business and Economics No. 2/2010 FURTHER INFORMATION
More informationTesting Statistical Hypotheses
E.L. Lehmann Joseph P. Romano Testing Statistical Hypotheses Third Edition 4y Springer Preface vii I Small-Sample Theory 1 1 The General Decision Problem 3 1.1 Statistical Inference and Statistical Decisions
More informationOn strategic complementarity conditions in Bertrand oligopoly
Economic Theory 22, 227 232 (2003) On strategic complementarity conditions in Bertrand oligopoly Rabah Amir 1 and Isabel Grilo 2 1 CORE and Department of Economics, Université Catholique de Louvain, 34
More informationThe profit function system with output- and input- specific technical efficiency
The profit function system with output- and input- specific technical efficiency Mike G. Tsionas December 19, 2016 Abstract In a recent paper Kumbhakar and Lai (2016) proposed an output-oriented non-radial
More informationLinearly interpolated FDH efficiency score for nonconvex frontiers
Journal of Multivariate Analysis 97 (26) 2141 2161 www.elsevier.com/locate/jmva Linearly interpolated FDH efficiency score for nonconvex frontiers Seok-Oh Jeong a, Léopold Simar b, a Department of Statistics,
More informationBootstrapping sequential change-point tests
Bootstrapping sequential change-point tests Claudia Kirch February 2008 Abstract In this paper we propose some bootstrapping methods to obtain critical values for sequential change-point tests. We consider
More informationAssessing the Effect of High Performance Computing Capabilities on Academic Research Output
Assessing the Effect of High Performance Computing Capabilities on Academic Research Output Amy W. Apon Linh B. Ngo Michael E. Payne Paul W. Wilson March 2014 Abstract This paper uses nonparametric methods
More informationDATA ENVELOPMENT ANALYSIS AND ITS APPLICATION TO THE MEASUREMENT OF EFFICIENCY IN HIGHER EDUCATION
DATA ENVELOPMENT ANALYSIS AND ITS APPLICATION TO THE MEASUREMENT OF EFFICIENCY IN HIGHER EDUCATION Jill Johnes* Department of Economics Lancaster University Management School Lancaster University Lancaster
More informationDepartment of Economics Working Paper Series
Department of Economics Working Paper Series Comparing Input- and Output-Oriented Measures of Technical Efficiency to Determine Local Returns to Scale in DEA Models Subhash C. Ray University of Connecticut
More informationA review of some semiparametric regression models with application to scoring
A review of some semiparametric regression models with application to scoring Jean-Loïc Berthet 1 and Valentin Patilea 2 1 ENSAI Campus de Ker-Lann Rue Blaise Pascal - BP 37203 35172 Bruz cedex, France
More information11. Bootstrap Methods
11. Bootstrap Methods c A. Colin Cameron & Pravin K. Trivedi 2006 These transparencies were prepared in 20043. They can be used as an adjunct to Chapter 11 of our subsequent book Microeconometrics: Methods
More informationDiscussion Paper Series
INSTITUTO TECNOLÓGICO AUTÓNOMO DE MÉXICO CENTRO DE INVESTIGACIÓN ECONÓMICA Discussion Paper Series Size Corrected Power for Bootstrap Tests Manuel A. Domínguez and Ignacio N. Lobato Instituto Tecnológico
More informationThe Number of Bootstrap Replicates in Bootstrap Dickey-Fuller Unit Root Tests
Working Paper 2013:8 Department of Statistics The Number of Bootstrap Replicates in Bootstrap Dickey-Fuller Unit Root Tests Jianxin Wei Working Paper 2013:8 June 2013 Department of Statistics Uppsala
More informationMULTI-COMPONENT RETURNS TO SCALE: A DEA-BASED APPROACH
Int. J. Contemp. Math. Sci., Vol. 1, 2006, no. 12, 583-590 MULTI-COMPONENT RETURNS TO SCALE: A DEA-BASED APPROACH Alireza Amirteimoori 1 Department of Mathematics P.O. Box: 41335-3516 Islamic Azad University,
More informationMore Technical Efficiency and Data Envelopment Analysis (DEA)
More Technical Efficiency and Data Envelopment Analysis (DEA) based on OnFront, Reference Guide Coelli, et al., Introduction to Efficiency and Productivity Springer, 2005, Ch 6. April 22, 2008 Technology:
More informationABSTRACT INTRODUCTION
Implementation of A Log-Linear Poisson Regression Model to Estimate the Odds of Being Technically Efficient in DEA Setting: The Case of Hospitals in Oman By Parakramaweera Sunil Dharmapala Dept. of Operations
More informationDo Markov-Switching Models Capture Nonlinearities in the Data? Tests using Nonparametric Methods
Do Markov-Switching Models Capture Nonlinearities in the Data? Tests using Nonparametric Methods Robert V. Breunig Centre for Economic Policy Research, Research School of Social Sciences and School of
More informationBootstrap, Jackknife and other resampling methods
Bootstrap, Jackknife and other resampling methods Part III: Parametric Bootstrap Rozenn Dahyot Room 128, Department of Statistics Trinity College Dublin, Ireland dahyot@mee.tcd.ie 2005 R. Dahyot (TCD)
More informationStatistical models and likelihood functions
Statistical models and likelihood functions Jean-Marie Dufour McGill University First version: February 1998 This version: February 11, 2008, 12:19pm This work was supported by the William Dow Chair in
More informationDefect Detection using Nonparametric Regression
Defect Detection using Nonparametric Regression Siana Halim Industrial Engineering Department-Petra Christian University Siwalankerto 121-131 Surabaya- Indonesia halim@petra.ac.id Abstract: To compare
More informationA comparison of four different block bootstrap methods
Croatian Operational Research Review 189 CRORR 5(014), 189 0 A comparison of four different block bootstrap methods Boris Radovanov 1, and Aleksandra Marcikić 1 1 Faculty of Economics Subotica, University
More informationLecture notes on statistical decision theory Econ 2110, fall 2013
Lecture notes on statistical decision theory Econ 2110, fall 2013 Maximilian Kasy March 10, 2014 These lecture notes are roughly based on Robert, C. (2007). The Bayesian choice: from decision-theoretic
More informationEstimation and Inference in Nonparametric Frontier Models: Recent Developments and Perspectives
Estimation and Inference in Nonparametric Frontier Models: Recent Developments and Perspectives Estimation and Inference in Nonparametric Frontier Models: Recent Developments and Perspectives Léopold Simar
More information2 P. L'Ecuyer and R. Simard otherwise perform well in the spectral test, fail this independence test in a decisive way. LCGs with multipliers that hav
Beware of Linear Congruential Generators with Multipliers of the form a = 2 q 2 r Pierre L'Ecuyer and Richard Simard Linear congruential random number generators with Mersenne prime modulus and multipliers
More informationSelection of the Appropriate Lag Structure of Foreign Exchange Rates Forecasting Based on Autocorrelation Coefficient
Selection of the Appropriate Lag Structure of Foreign Exchange Rates Forecasting Based on Autocorrelation Coefficient Wei Huang 1,2, Shouyang Wang 2, Hui Zhang 3,4, and Renbin Xiao 1 1 School of Management,
More informationNonparametric production technologies with multiple component processes
Loughborough University Institutional Repository Nonparametric production technologies with multiple component processes This item was submitted to Loughborough University's Institutional Repository by
More informationPreliminaries The bootstrap Bias reduction Hypothesis tests Regression Confidence intervals Time series Final remark. Bootstrap inference
1 / 171 Bootstrap inference Francisco Cribari-Neto Departamento de Estatística Universidade Federal de Pernambuco Recife / PE, Brazil email: cribari@gmail.com October 2013 2 / 171 Unpaid advertisement
More informationCalibration Estimation of Semiparametric Copula Models with Data Missing at Random
Calibration Estimation of Semiparametric Copula Models with Data Missing at Random Shigeyuki Hamori 1 Kaiji Motegi 1 Zheng Zhang 2 1 Kobe University 2 Renmin University of China Institute of Statistics
More informationVolume 29, Issue 1. On the Importance of Span of the Data in Univariate Estimation of the Persistence in Real Exchange Rates
Volume 29, Issue 1 On the Importance of Span of the Data in Univariate Estimation of the Persistence in Real Exchange Rates Hyeongwoo Kim Auburn University Young-Kyu Moh Texas Tech University Abstract
More informationResampling and the Bootstrap
Resampling and the Bootstrap Axel Benner Biostatistics, German Cancer Research Center INF 280, D-69120 Heidelberg benner@dkfz.de Resampling and the Bootstrap 2 Topics Estimation and Statistical Testing
More informationROBUST NONPARAMETRIC FRONTIER ESTIMATORS: QUALITATIVE ROBUSTNESS AND INFLUENCE FUNCTION
Statistica Sinica 16(26), 1233-1253 ROBUST NONPARAMETRIC FRONTIER ESTIMATORS: QUALITATIVE ROBUSTNESS AND INFLUENCE FUNCTION Abdelaati Daouia and Anne Ruiz-Gazen Université Paul Sabatier and Université
More informationD I S C U S S I O N P A P E R
I N S T I T U T D E S T A T I S T I Q U E B I O S T A T I S T I Q U E E T S C I E N C E S A C T U A R I E L L E S ( I S B A ) UNIVERSITÉ CATHOLIQUE DE LOUVAIN D I S C U S S I O N P A P E R 2014/06 Adaptive
More informationNonparametric Inference via Bootstrapping the Debiased Estimator
Nonparametric Inference via Bootstrapping the Debiased Estimator Yen-Chi Chen Department of Statistics, University of Washington ICSA-Canada Chapter Symposium 2017 1 / 21 Problem Setup Let X 1,, X n be
More informationCentre for Efficiency and Productivity Analysis
Centre for Efficiency and Productivity Analysis Working Paper Series No. WP02/2013 Scale Efficiency and Homotheticity: Equivalence of Primal and Dual Measures Valentin Zelenyuk Date: February 2013 School
More informationStrategic Manipulation and Regular Decomposition of Fuzzy Preference Relations
Strategic Manipulation and Regular Decomposition of Fuzzy Preference Relations Olfa Meddeb, Fouad Ben Abdelaziz, José Rui Figueira September 27, 2007 LARODEC, Institut Supérieur de Gestion, 41, Rue de
More informationPrediction of A CRS Frontier Function and A Transformation Function for A CCR DEA Using EMBEDED PCA
03 (03) -5 Available online at www.ispacs.com/dea Volume: 03, Year 03 Article ID: dea-0006, 5 Pages doi:0.5899/03/dea-0006 Research Article Data Envelopment Analysis and Decision Science Prediction of
More informationIndependent and conditionally independent counterfactual distributions
Independent and conditionally independent counterfactual distributions Marcin Wolski European Investment Bank M.Wolski@eib.org Society for Nonlinear Dynamics and Econometrics Tokyo March 19, 2018 Views
More informationA Bootstrap Test for Conditional Symmetry
ANNALS OF ECONOMICS AND FINANCE 6, 51 61 005) A Bootstrap Test for Conditional Symmetry Liangjun Su Guanghua School of Management, Peking University E-mail: lsu@gsm.pku.edu.cn and Sainan Jin Guanghua School
More informationInference via Kernel Smoothing of Bootstrap P Values
Queen s Economics Department Working Paper No. 1054 Inference via Kernel Smoothing of Bootstrap P Values Jeff Racine McMaster University James G. MacKinnon Queen s University Department of Economics Queen
More informationBootstrap Tests: How Many Bootstraps?
Bootstrap Tests: How Many Bootstraps? Russell Davidson James G. MacKinnon GREQAM Department of Economics Centre de la Vieille Charité Queen s University 2 rue de la Charité Kingston, Ontario, Canada 13002
More informationgroup Jean-Eric Pin and Christophe Reutenauer
A conjecture on the Hall topology for the free group Jean-Eric Pin and Christophe Reutenauer Abstract The Hall topology for the free group is the coarsest topology such that every group morphism from the
More informationTesting Statistical Hypotheses
E.L. Lehmann Joseph P. Romano, 02LEu1 ttd ~Lt~S Testing Statistical Hypotheses Third Edition With 6 Illustrations ~Springer 2 The Probability Background 28 2.1 Probability and Measure 28 2.2 Integration.........
More informationFinancial Econometrics and Volatility Models Copulas
Financial Econometrics and Volatility Models Copulas Eric Zivot Updated: May 10, 2010 Reading MFTS, chapter 19 FMUND, chapters 6 and 7 Introduction Capturing co-movement between financial asset returns
More informationRobust Backtesting Tests for Value-at-Risk Models
Robust Backtesting Tests for Value-at-Risk Models Jose Olmo City University London (joint work with Juan Carlos Escanciano, Indiana University) Far East and South Asia Meeting of the Econometric Society
More informationUsing the Delta Test for Variable Selection
Using the Delta Test for Variable Selection Emil Eirola 1, Elia Liitiäinen 1, Amaury Lendasse 1, Francesco Corona 1, and Michel Verleysen 2 1 Helsinki University of Technology Lab. of Computer and Information
More informationValued relations aggregation with the Borda method.
Valued relations aggregation with the Borda method. Thierry Marchant* Service de mathématiques de la gestion, Université Libre de Bruxelles, Boulevard du Triomphe CP210-01, 1050 Bruxelles, Belgium. Tél
More informationCentre for Efficiency and Productivity Analysis
Centre for Efficiency and Productivity Analysis Working Paper Series No. WP04/2018 Profit Efficiency, DEA, FDH and Big Data Valentin Zelenyuk Date: June 2018 School of Economics University of Queensland
More informationA first look at the performances of a Bayesian chart to monitor. the ratio of two Weibull percentiles
A first loo at the performances of a Bayesian chart to monitor the ratio of two Weibull percentiles Pasquale Erto University of Naples Federico II, Naples, Italy e-mail: ertopa@unina.it Abstract. The aim
More informationthe long tau-path for detecting monotone association in an unspecified subpopulation
the long tau-path for detecting monotone association in an unspecified subpopulation Joe Verducci Current Challenges in Statistical Learning Workshop Banff International Research Station Tuesday, December
More informationRevenue Malmquist Index with Variable Relative Importance as a Function of Time in Different PERIOD and FDH Models of DEA
Revenue Malmquist Index with Variable Relative Importance as a Function of Time in Different PERIOD and FDH Models of DEA Mohammad Ehsanifar, Golnaz Mohammadi Department of Industrial Management and Engineering
More informationFunctional Radial Basis Function Networks (FRBFN)
Bruges (Belgium), 28-3 April 24, d-side publi., ISBN 2-9337-4-8, pp. 313-318 Functional Radial Basis Function Networks (FRBFN) N. Delannay 1, F. Rossi 2, B. Conan-Guez 2, M. Verleysen 1 1 Université catholique
More informationBOOTSTRAPPING DIFFERENCES-IN-DIFFERENCES ESTIMATES
BOOTSTRAPPING DIFFERENCES-IN-DIFFERENCES ESTIMATES Bertrand Hounkannounon Université de Montréal, CIREQ December 2011 Abstract This paper re-examines the analysis of differences-in-differences estimators
More informationSpecial Cases in Linear Programming. H. R. Alvarez A., Ph. D. 1
Special Cases in Linear Programming H. R. Alvarez A., Ph. D. 1 Data Envelopment Analysis Objective To compare technical efficiency of different Decision Making Units (DMU) The comparison is made as a function
More informationI N S T I T U T D E S T A T I S T I Q U E B I O S T A T I S T I Q U E E T S C I E N C E S A C T U A R I E L L E S (I S B A)
I N S T I T U T D E S T A T I S T I Q U E B I O S T A T I S T I Q U E E T S C I E N C E S A C T U A R I E L L E S (I S B A) UNIVERSITÉ CATHOLIQUE DE LOUVAIN D I S C U S S I O N P A P E R /9 HOW TO MEASURE
More informationPreliminaries The bootstrap Bias reduction Hypothesis tests Regression Confidence intervals Time series Final remark. Bootstrap inference
1 / 172 Bootstrap inference Francisco Cribari-Neto Departamento de Estatística Universidade Federal de Pernambuco Recife / PE, Brazil email: cribari@gmail.com October 2014 2 / 172 Unpaid advertisement
More informationA Simple, Graphical Procedure for Comparing Multiple Treatment Effects
A Simple, Graphical Procedure for Comparing Multiple Treatment Effects Brennan S. Thompson and Matthew D. Webb May 15, 2015 > Abstract In this paper, we utilize a new graphical
More informationIdentifying Efficient Units in Large-Scale Dea Models
Pyry-Antti Siitari Identifying Efficient Units in Large-Scale Dea Models Using Efficient Frontier Approximation W-463 Pyry-Antti Siitari Identifying Efficient Units in Large-Scale Dea Models Using Efficient
More informationD I S C U S S I O N P A P E R
I N S T I T U T D E S T A T I S T I Q U E B I O S T A T I S T I Q U E E T S C I E N C E S A C T U A R I E L L E S ( I S B A ) UNIVERSITÉ CATHOLIQUE DE LOUVAIN D I S C U S S I O N P A P E R 2014/16 Efficiency
More informationPublic Sector Management I
Public Sector Management I Produktivitätsanalyse Introduction to Efficiency and Productivity Measurement Note: The first part of this lecture is based on Antonio Estache / World Bank Institute: Introduction
More informationSensitivity and Stability Analysis in Uncertain Data Envelopment (DEA)
Sensitivity and Stability Analysis in Uncertain Data Envelopment (DEA) eilin Wen a,b, Zhongfeng Qin c, Rui Kang b a State Key Laboratory of Virtual Reality Technology and Systems b Department of System
More informationA Refined Bootstrap for Heavy Tailed Distributions
A Refined Bootstrap for Heavy Tailed Distributions by Adriana Cornea GREQAM Centre de la Vieille Charité 2, rue de la Charité 13236 Marseille cedex 02, France email: adrianacornea@univmedfr and Russell
More informationPAijpam.eu ADAPTIVE K-S TESTS FOR WHITE NOISE IN THE FREQUENCY DOMAIN Hossein Arsham University of Baltimore Baltimore, MD 21201, USA
International Journal of Pure and Applied Mathematics Volume 82 No. 4 2013, 521-529 ISSN: 1311-8080 (printed version); ISSN: 1314-3395 (on-line version) url: http://www.ijpam.eu doi: http://dx.doi.org/10.12732/ijpam.v82i4.2
More informationStatistics - Lecture One. Outline. Charlotte Wickham 1. Basic ideas about estimation
Statistics - Lecture One Charlotte Wickham wickham@stat.berkeley.edu http://www.stat.berkeley.edu/~wickham/ Outline 1. Basic ideas about estimation 2. Method of Moments 3. Maximum Likelihood 4. Confidence
More informationDepartment of Economics, Vanderbilt University While it is known that pseudo-out-of-sample methods are not optimal for
Comment Atsushi Inoue Department of Economics, Vanderbilt University (atsushi.inoue@vanderbilt.edu) While it is known that pseudo-out-of-sample methods are not optimal for comparing models, they are nevertheless
More informationBootstrapping the Grainger Causality Test With Integrated Data
Bootstrapping the Grainger Causality Test With Integrated Data Richard Ti n University of Reading July 26, 2006 Abstract A Monte-carlo experiment is conducted to investigate the small sample performance
More informationContributions to extreme-value analysis
Contributions to extreme-value analysis Stéphane Girard INRIA Rhône-Alpes & LJK (team MISTIS). 655, avenue de l Europe, Montbonnot. 38334 Saint-Ismier Cedex, France Stephane.Girard@inria.fr February 6,
More informationThe Power of Bootstrap and Asymptotic Tests
The Power of Bootstrap and Asymptotic Tests GREQAM Centre de la Vieille Charité 2 rue de la Charité 13002 Marseille, France by Russell Davidson email: russell@ehess.cnrs-mrs.fr and James G. MacKinnon Department
More informationDarmstadt Discussion Papers in ECONOMICS
Darmstadt Discussion Papers in ECONOMICS Direct Targeting of Efficient DMUs for Benchmarking Jens J. Krüger Nr. 229 Arbeitspapiere der Volkswirtschaftlichen Fachgebiete der TU Darmstadt ISSN: 1438-2733
More informationConfidence intervals for kernel density estimation
Stata User Group - 9th UK meeting - 19/20 May 2003 Confidence intervals for kernel density estimation Carlo Fiorio c.fiorio@lse.ac.uk London School of Economics and STICERD Stata User Group - 9th UK meeting
More informationA NON-PARAMETRIC TEST FOR NON-INDEPENDENT NOISES AGAINST A BILINEAR DEPENDENCE
REVSTAT Statistical Journal Volume 3, Number, November 5, 155 17 A NON-PARAMETRIC TEST FOR NON-INDEPENDENT NOISES AGAINST A BILINEAR DEPENDENCE Authors: E. Gonçalves Departamento de Matemática, Universidade
More informationBootstrapping Heteroskedasticity Consistent Covariance Matrix Estimator
Bootstrapping Heteroskedasticity Consistent Covariance Matrix Estimator by Emmanuel Flachaire Eurequa, University Paris I Panthéon-Sorbonne December 2001 Abstract Recent results of Cribari-Neto and Zarkos
More informationFUNCTIONAL DATA ANALYSIS. Contribution to the. International Handbook (Encyclopedia) of Statistical Sciences. July 28, Hans-Georg Müller 1
FUNCTIONAL DATA ANALYSIS Contribution to the International Handbook (Encyclopedia) of Statistical Sciences July 28, 2009 Hans-Georg Müller 1 Department of Statistics University of California, Davis One
More informationFurther discussion on linear production functions and DEA
European Journal of Operational Research 127 (2000) 611±618 www.elsevier.com/locate/dsw Theory and Methodology Further discussion on linear production functions and DEA Joe Zhu * Department of Management,
More informationRobust Performance Hypothesis Testing with the Variance. Institute for Empirical Research in Economics University of Zurich
Institute for Empirical Research in Economics University of Zurich Working Paper Series ISSN 1424-0459 Working Paper No. 516 Robust Performance Hypothesis Testing with the Variance Olivier Ledoit and Michael
More informationLIST OF PUBLICATIONS. 1. J.-P. Kreiss and E. Paparoditis, Bootstrap for Time Series: Theory and Applications, Springer-Verlag, New York, To appear.
LIST OF PUBLICATIONS BOOKS 1. J.-P. Kreiss and E. Paparoditis, Bootstrap for Time Series: Theory and Applications, Springer-Verlag, New York, To appear. JOURNAL PAPERS 61. D. Pilavakis, E. Paparoditis
More information